Method and system for detecting rearview mirror viewing behavior of driver

Abstract

The invention discloses a method and a system for detecting a rearview mirror viewing behavior of a driver. The method comprises the steps of acquiring a cab image by a vehicle-mounted video system; taking a face and neck visible skin region of the driver as an image analysis processing object; setting an algorithm for adaptive learning and tracing identification of the face and neck visible skin region; extracting a face and neck visible skin outer contour; taking a lowest point of the neck of the face and neck visible skin outer contour as a basic point; dividing the face and neck visible skin outer contour into a left part and a right part by a vertical line passing the basic point; defining an area ratio of the left and right parts as a feature parameter; obtaining a reference eigenvalue of the feature parameter; and judging whether the rearview mirror viewing behavior exists or not according to a numerical relationship between the current feature parameter and the reference eigenvalue in combination with a stare threshold and a duration threshold. The detection system is simple in structure; and the detection method has relatively high accuracy rate and good adaptive learning capability and anti-jamming capability, is high in detection efficiency, and can meet real-time detection and reminding requirements of the rearview mirror viewing behavior during quick running of a vehicle.

Description

technical field [0001] The present invention relates to the technical field of vehicle safety, and more specifically, relates to a system that can automatically detect whether the driver has effectively checked the rearview mirror during steering maneuvers such as turning, merging, and changing lanes, and make corresponding reminders accordingly. methods and systems. Background technique [0002] With the rapid increase of the number of motor vehicles and the high incidence of traffic accidents, traffic safety has become a common concern. Statistics show that 25% to 30% of traffic accidents are directly related to the driver's attention state, among which steering manipulation processes such as turning, merging, and changing lanes are one of the main occasions where traffic accidents occur, especially when drivers Failure to pay attention to traffic information behind the turning side of the vehicle. The real-time detection and necessary reminder of rearview mirror viewing...

AI Technical Summary

Problems solved by technology

Due to the application of face models and / or detailed features, the algorithm is relatively complex and may easily lead to insufficient real-time detection when the vehicle is driving at high speed

Although the method only for facial contours reduces the ability to express detailed information and improves the real-time performance of the algorithm, the selection of positioning references when defining facial geometric features is often easily disturbed

In addition, these situations are lacking in adaptive learning capabilities, and most of them need to rely on pre-set templates or feature parameters that are closely related to each driver. The detection accuracy may be affected when it is large (such as when the wearing object is blocked) or the imaging angle changes (such as when the seat is adjusted)

[0004] CN201110394497.6 discloses a "Pattern Recognition-Based Safe Driving Monitoring System and Method", which mentions the positioning and segmentation of the driver's face through the facial skin color detection method, but ultimately for the extraction of facial features , also has defects such as poor real-time performance and susceptibility to interference

Images